Skip to content

Latest commit

 

History

History
107 lines (70 loc) · 4.91 KB

README.md

File metadata and controls

107 lines (70 loc) · 4.91 KB
Raw
Boost your Next.js projects with AI.

GPTBundle

GPTBundle is an open-source library designed to empower Next.JS web developers by integrating cutting-edge GPT-4 capabilities into their next launches.

Leveraging the power of LLM models (used by ChatGPT) through OpenAI's public API, GPTBundle offers developers a range of templates built using Vercel's Next.js and react-jsonschema-form. Our ultimate goal is to help the development community to create AI-powered web features easily.

Key Features · Documentation · Project Structure · Contributing ·

Key Features

AI Assistant Button

GPTBundle offers AI buttons that auto-fill and improve the user-provided data in multiple text fields. They are flexible to fit in any form and in can use them to help users create data such as bios based on avaiable profile info, task descriptions based on the context provided, and much more.

AI Form Creator Templates

Choose from a variety of templates tailored for common formats of web features, such as creating a filling form for legal contracts, creating exams based on technical articles, creating a shopping checklist based on a cooking recipe, text enhancement for marketing content, and more.

Compatible with Major UI Libraries

By implementing react-jsonschema-form's versatility, GPTBundle is compatible with major UI libraries used in many renowned web products: Ant Design — Bootstrap 3 — Bootstrap 4 — Chakra UI — Fluent UI — Fluent UI 9 — Material UI 4 — Material UI 5 — Semantic UI

Open Source

GPTBundle is developed by Vinta and maintained by the community, ensuring transparency, reliability, and continuous improvement. It will always be open to feedback and suggestions.

Documentation

Documentation: https://docs.gptbundle.ai/

In our public documentation, you'll find installation instructions, tutorials, and examples. Note that hosted examples are not interactive since they need an OpenAI API Key to work.

Note that hosted examples are not interactive. See Building below to learn how to build the interactive docs.

Project Structure

This is a multipackage monorepo that holds the two NPM projects necessary for GPTBundle:

  • @gptbundle/client
  • @gptbundle/server

Both are stored at packages/ directory.

Contributing

Pre-commit

Set up Husky in your local git repository:

pnpm run prepare

Building

For building locally, run pnpm run build or pnpm run build:watch.

Interactive Documentation

Run the docs locally to access the interactive examples.

Create a .env.local file inside docs/ and set the Open AI API Key there:

# docs/.env.local
OPENAI_API_KEY=sk-...

Run the docs project:

pnpm -F @gptbundle/docs run dev

Then open http://localhost:3000 in your browser.

Running Tests

There are three available commands for running tests:

  1. pnpm run test or pnpm test – runs all test cases.
  2. pnpm run test:cov – runs all tests and generates a coverage report.
  3. pnpm run test:watch – runs all tests in watch mode.

NOTE: Running these commands in the root directory will trigger all tests from all packages. However, if you run them within a specific package directory, only the tests associated with that package will be executed.

This library is created and maintaned by Vinta Software — by developers, and for developers.

For questions, feedback, and partnerships don't hesitate to reach us at gptbundle@vintasoftware.com